{"id":"W2139555052","doi":"10.1287/opre.2014.1332","title":"Myopic Bounds for Optimal Policy of POMDPs: An Extension of Lovejoy’s Structural Results","year":2015,"lang":"en","type":"article","venue":"Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Extension (predicate logic); Bounded function; Markov decision process; Mathematical optimization; Computer science; Relaxation (psychology); Upper and lower bounds; Mathematical economics; Mathematics; Markov process","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006305123,0.00147416,0.001748048,0.001660856,0.001069086,0.002266815,0.002684369,0.001630413,0.007790913],"category_scores_gemma":[0.03567569,0.001595276,0.001955071,0.0011693,0.003331993,0.007508744,0.004238229,0.005633146,0.0007649835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0024529,"about_ca_system_score_gemma":0.003049222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001776388,"about_ca_topic_score_gemma":0.001648782,"domain_scores_codex":[0.9954919,0.001404039,0.0002458193,0.0007585945,0.00164038,0.0004592745],"domain_scores_gemma":[0.971943,0.02179096,0.00186182,0.001867034,0.00182358,0.0007135637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001107157,0.00008255529,0.00043453,0.0002691128,0.0000428753,0.00009601684,0.0003478986,0.2843559,0.001817022,0.6926653,0.001779272,0.01799877],"study_design_scores_gemma":[0.00003487602,0.00008162056,0.0002345261,0.0001109826,0.0000161575,0.0000456899,0.00005291197,0.5260627,0.001217177,0.4692478,0.002866687,0.00002894298],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01158186,0.000501799,0.9743298,0.001065947,0.00005562373,0.00007056233,0.000184121,0.0001725683,0.01203775],"genre_scores_gemma":[0.7592381,0.001734831,0.2305493,0.0007647976,0.0003521981,0.0007733515,0.0004963414,0.0004054193,0.005685611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007790913,"threshold_uncertainty_score":0.0333451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2253839206477561,"score_gpt":0.4734528638194654,"score_spread":0.2480689431717093,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}